Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 688 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0887. Min Range: -2.0887
Max Act: 2.0887. Min Act: -0.0001
Data Index: 651656 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.9847. Min Act: -0.0001
Data Index: 164504 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0887. Min Range: -2.0887
Max Act: 2.0666. Min Act: -0.0001
Data Index: 795364 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.8826. Min Act: -0.0002
Data Index: 451392 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0887. Min Range: -2.0887
Max Act: 2.0473. Min Act: -0.0001
Data Index: 569213 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.6523. Min Act: -0.0001
Data Index: 926113 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.8518. Min Act: -0.0001
Data Index: 914434 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.5965. Min Act: -0.0001
Data Index: 111213 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.7153. Min Act: -0.0002
Data Index: 1097556 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.7204. Min Act: -0.0001
Data Index: 557836 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.7062. Min Act: -0.0001
Data Index: 1125774 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.6659. Min Act: -0.0001
Data Index: 84914 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.6443. Min Act: -0.0002
Data Index: 47232 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.8205. Min Act: -0.0001
Data Index: 1345288 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.5554. Min Act: -0.0001
Data Index: 331783 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.7060. Min Act: -0.0001
Data Index: 498407 (C4 (Web Text))
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.7061. Min Act: -0.0001
Data Index: 108453 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.6940. Min Act: -0.0002
Data Index: 278884 (C4 (Web Text))
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.5585. Min Act: -0.0001
Data Index: 691611 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0887. Min Range: -2.0887
Max Act: 1.6377. Min Act: -0.0002
Data Index: 853745 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #19